
import re
import time
import string
import ast
import random

from tqdm.notebook import tqdm
from IPython.display import Markdown

import pandas as pd
import numpy as np
import plotly.express as px
import plotly.graph_objects as go

from functools import partial
from umap import UMAP
from hdbscan import HDBSCAN
from bertopic import BERTopic

from nltk.corpus import stopwords
import nltk

import torch
from datasets import Dataset
import datasets
import evaluate

from sklearn.feature_extraction.text import CountVectorizer
from sentence_transformers import SentenceTransformer
from peft import LoraConfig, get_peft_model, TaskType, PeftModel, PeftConfig
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer, TrainingArguments, Trainer, GenerationConfig


tqdm.pandas()
nltk.download('stopwords')

[nltk_data] Downloading package stopwords to /root/nltk_data...
[nltk_data]   Package stopwords is already up-to-date!

True


df = pd.read_csv("data/raw_data/twcs.csv")
df.head()


df.describe()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2811774 entries, 0 to 2811773
Data columns (total 7 columns):
 #   Column                   Dtype  
---  ------                   -----  
 0   tweet_id                 int64  
 1   author_id                object 
 2   inbound                  bool   
 3   created_at               object 
 4   text                     object 
 5   response_tweet_id        object 
 6   in_response_to_tweet_id  float64
dtypes: bool(1), float64(1), int64(1), object(4)
memory usage: 131.4+ MB


autor_count = df.groupby('author_id').size().reset_index(name='count').sort_values(['count'], ascending=False)[:20]
fig = px.pie(autor_count, names=autor_count.author_id, values='count', title='Top 20 Company Names')
fig.show()


df['date'] = pd.to_datetime(df['created_at'], format='%a %b %d %H:%M:%S +0000 %Y')
date_counts = df['date'].dt.date.value_counts().reset_index()
date_counts.columns = ['date', 'count']
date_counts = date_counts.sort_values(by='date')


date_counts.quantile(0.90)

count    84.4
Name: 0.9, dtype: float64


fig = px.box(date_counts, y='count')
fig.update_layout(title='Date Distribution', xaxis_title='Count')
fig.show()


fig = px.line(date_counts, x='date', y='count', title='Number of Tweets by Date')
fig.show()


df = df[df['date'] > pd.to_datetime('2017-09-01')]


def clean_text(text):
    # Replace URLs with "the web site"
    text = re.sub(r'http\S+|www\S+|https\S+', 'the url', text)
    
    # Remove words starting with "@"
    text = re.sub(r'\B@\w+', '', text)
    
    # Remove symbols and emojis
    text = re.sub(r'[^\w\s,.:\'!?-]', '', text)
    
    # Remove all punctuations except ",", ".", ":", "'", "?", "!","-"
    punctuations_to_keep = ',.:\'!?-'
    text = ''.join([char if char in string.ascii_letters + string.digits + punctuations_to_keep else ' ' for char in text])
    
    # Remove non-ascii characters
    text = ''.join([char for char in text if ord(char) < 128])
        
    # Remove two letters coming after "-"
    text = re.sub(r'\s*-\w{2}\b', '', text)
    
    # Remove unnecessary blanks
    text = re.sub(r'\s+', ' ', text)
    
    # Make all words lowercase
    text = text.lower()
        
    return text.strip()


# Apply cleaning
df['text'] = df['text'].progress_apply(lambda x: clean_text(x))
df.head()

  0%|          | 0/2804129 [00:00<?, ?it/s]


df_starting = df[df['in_response_to_tweet_id'].isna()]
df_starting.head()


df = df.set_index('tweet_id')


def display_markdown(input_list):
    markdown_str = "\n\n".join([">{}".format(item) for item in input_list])
    display(Markdown(markdown_str))


def isNaN(num):
    return num!= num


def create_conversations(df, conversation_id, index):
    if conversation_id is None:
        conversation_id = []
        
    try: 
        row = df.loc[index]
        conversation_id.append(index)
    except KeyError:
        return df.loc[conversation_id].text.values.tolist()    
    
    response = row.response_tweet_id
    if not pd.isna(response):
        next_index = ast.literal_eval(response)
        if isinstance(next_index, tuple):
            create_conversations(df, conversation_id, next_index[0])
        else:
            create_conversations(df , conversation_id, next_index)
        
    return df.loc[conversation_id].text.values.tolist()


conv_list = create_conversations(df=df, conversation_id=None, index=18)


display_markdown(conv_list)


create_conversations_partial = partial(create_conversations, df, None)
all_conversation = df_starting['tweet_id'].progress_map(lambda x: create_conversations_partial(x))

  0%|          | 0/652770 [00:00<?, ?it/s]


# Saving and loading
# np.save("data/conversations/all_conversation.npy", all_conversation)
all_conversation = np.load("data/conversations/all_conversation.npy", allow_pickle=True)


# Example
display_markdown(all_conversation[0])


# Sampling 20% of all conversations
#all_conversation_sampled = np.random.choice(all_conversation, size=int(len(all_conversation) * 0.2), replace=False)

# Saving and Loading
#np.save("data/conversations/all_conversation_sampled.npy", pd.Series(all_conversation_sampled))
all_conversation_sampled = np.load("data/conversations/all_conversation_sampled.npy", allow_pickle=True)


# Example
display_markdown(all_conversation_sampled[10])


all_conversation_sampled_flatten = [item for sublist in all_conversation_sampled for item in sublist]
len(all_conversation_sampled_flatten)

377393


# Select Embedding model
embedding_model = SentenceTransformer('all-MiniLM-L6-v2')


# Configure the dimention reduction algorithm (I used UMAP)
umap_model = UMAP(n_neighbors=5, n_components=5)


# Configure the clustring algorithm (I used HDBSCAN)
hdbscan_model = HDBSCAN(min_cluster_size=256, min_samples=64,
                        gen_min_span_tree=True,
                        prediction_data=True)


stopwords = list(stopwords.words('english'))
# we add this to remove stopwords that can pollute topcs
vectorizer_model = CountVectorizer(ngram_range=(1, 2), stop_words=stopwords)

model_bert_topic = BERTopic(
    umap_model=umap_model,
    hdbscan_model=hdbscan_model,
    embedding_model=embedding_model,
    vectorizer_model=vectorizer_model,
    top_n_words=5,
    language='english',
    calculate_probabilities=True,
    verbose=True
)
topics, probs = model_bert_topic.fit_transform(all_conversation_sampled_flatten)

[nltk_data] Downloading package stopwords to /root/nltk_data...
[nltk_data]   Package stopwords is already up-to-date!

Batches:   0%|          | 0/11794 [00:00<?, ?it/s]

2023-08-05 19:14:02,843 - BERTopic - Transformed documents to Embeddings
2023-08-05 19:22:54,702 - BERTopic - Reduced dimensionality
2023-08-05 19:36:16,535 - BERTopic - Clustered reduced embeddings


# Saving and Loading
# model_bert_topic.save("data/models/bert_topic/model", serialization="safetensors", save_ctfidf=True, save_embedding_model=embedding_model)
model_bert_topic = BERTopic.load("data/models/bert_topic/model")


model_bert_topic.get_topic_info()


model_bert_topic.visualize_topics()


model_bert_topic.visualize_barchart(top_n_topics=12)


def get_all_docs_per_topic(topics):
    topic_docs = {topic: [] for topic in set(topics)}
    for topic, doc in zip(topics, all_conversation_sampled_flatten):
        topic_docs[topic].append(doc)
    return topic_docs    

def get_all_conversation_by_topic(topic, topic_docs, all_conversation):
    conversations = []
    for doc in tqdm(topic_docs[topic]):
        for conv in all_conversation_sampled:
            if doc in conv and conv not in conversations:
                conversations.append(conv)
    return conversations            
    
                          
topics = model_bert_topic.topics_

topic_docs = get_all_docs_per_topic(topics)
delivery_conv  = get_all_conversation_by_topic(
    topic=8, topic_docs=topic_docs, all_conversation=all_conversation_sampled)

  0%|          | 0/4201 [00:00<?, ?it/s]


# The number of conversations discussing about the order and delivery service  
len(delivery_conv)

3250


# Example
display_markdown(delivery_conv[500])


def split_comment_response(conversations):
    
    comments = []
    responses = []
    for conv in conversations:
        if len(conv) > 1:
            comments.append(conv[0])
            responses.append(conv[1])
        else:
            continue
    
    return comments, responses


comments , responses = split_comment_response(delivery_conv)
assert len(comments) == len(responses)


print(len(comments))

3227


display_markdown([comments[188]])


display_markdown([responses[188]])


model_name='google/flan-t5-base'

original_model = AutoModelForSeq2SeqLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_name)


# Zero shot prompt
def generate_prompt(comment):
    template = f"""As a member of the customer support team, you must use the following guidelines to respond to customers who have expressed complaints or askes a question about the service they received. Your task is to generate a helpful and empathetic response to address the customer's concerns effectively.

Please ensure that the generated response follows these guidelines:

1. Start the response with a polite and courteous greeting to the customer.

2. If there is a complaint,  express empathy and understanding towards the customer's complaint.

3. If there is a complaint, provide a sincere apology for any inconvenience caused by the service issue.

4. If there is a complaint, provide a sincere apology for any inconvenience caused by the service issue.

5. If there is a question, provide the required information to answer the question. 

6. Clearly address the specific points raised in the customer's complaint.

7. Explain the steps or actions being taken to resolve the issue.

8. Offer any necessary compensation or remedies, if applicable.

9. Encourage the customer to reach out for further assistance if needed.

10. End the response with another polite expression of gratitude and willingness to assist.

Customer's Complaint: {comment}

Your Generated Response:
     """
    return template


# Few shot prompt
def generate_prompt_few_shot(comment):
    template = f"""As a member of the customer support team, you must use the following guidelines to respond to customers who have expressed complaints or askes a question about the service they received. Your task is to generate a helpful and empathetic response to address the customer's concerns effectively.

Please ensure that the generated response follows these guidelines:

1. Start the response with a polite and courteous greeting to the customer.

2. If there is a complaint,  express empathy and understanding towards the customer's complaint.

3. If there is a complaint, provide a sincere apology for any inconvenience caused by the service issue.

4. If there is a complaint, provide a sincere apology for any inconvenience caused by the service issue.

5. If there is a question, provide the required information to answer the question. 

6. Clearly address the specific points raised in the customer's complaint.

7. Explain the steps or actions being taken to resolve the issue.

8. Offer any necessary compensation or remedies, if applicable.

9. Encourage the customer to reach out for further assistance if needed.

10. End the response with another polite expression of gratitude and willingness to assist.

    Example 1:
    Customer's Expression: I contacted seller and was rudely hung up on several times scam.
    Your Response: I'm sorry for the troubles with your order! have you tried to contact us here?

    Example 2:
    Customer's Expression: Amazonhelp got the prime trial, but didn't give us discount on one item.
    Your Response: Prime offers free shipping on items shipped by amazon. what discount are you referring to? 

    Example 3:
    Customer's Expression: Argoshelpers hi there i pre ordered the xbox one x i'm enquiring if i will be receiving it today?
    Your Generated Response: Can i have the order number and your full address please and i will look into it.

    Customer's Expression: {comment}
    Your Response:
    
 """
    return template


def split_data(inputs, labels, test_size=25):
    data = list(zip(inputs, labels))

    # Shuffle the data randomly
    random.shuffle(data)

    # Split into test and train sets
    test_data = data[:test_size]
    train_data = data[test_size:]

    test_inputs, test_labels = zip(*test_data)
    train_inputs, train_labels = zip(*train_data)

    return train_inputs, train_labels, test_inputs, test_labels

train_comments, train_responses, test_comments, test_responses = split_data(comments, responses)

# np.save('data/test_train/test_comments.npy', test_comments)
# np.save('data/test_train/train_comments.npy', train_comments)
# np.save('data/test_train/test_responses.npy', test_responses)
# np.save('data/test_train/train_responses.npy', train_responses)


test_comments = np.load('data/test_train/test_comments.npy')
train_comments = np.load('data/test_train/train_comments.npy')
test_responses = np.load('data/test_train/test_responses.npy')
train_responses = np.load('data/test_train/train_responses.npy')


print("number_of_train_data: {}".format(len(train_comments)))
print("number_of_test_data: {}".format(len(test_comments)))

number_of_train_data: 3202
number_of_test_data: 25


def generate_respond(comment, model, tokenizer):
    prompt = generate_prompt_few_shot(comment)
    input_ids = tokenizer(prompt, return_tensors='pt').input_ids
    output = tokenizer.decode(
        model.generate(
            input_ids=input_ids,
            max_new_tokens=500,
            do_sample=True,
            temperature= 0.7)[0],
        skip_special_tokens=True
    )

    return output

results = {}
for comment, response in tqdm(zip(test_comments, test_responses)):
    output = generate_respond(comment, original_model, tokenizer)
    results[comment] = {"human": response, "original_model": output}

0it [00:00, ?it/s]


pd.set_option('display.max_colwidth', 500)
original_model_reponse = pd.DataFrame.from_dict(results).T.reset_index()
original_model_reponse = original_model_reponse.rename(columns={"index":"comment"})
original_model_reponse


model_name='google/flan-t5-base'
original_model = AutoModelForSeq2SeqLM.from_pretrained(model_name, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_name)


conversation_dataset = {}
conversation_dataset['comments'] = train_comments
conversation_dataset['responses'] = train_responses

dataset = Dataset.from_dict(conversation_dataset)

def tokenize_function(example):
    prompt = [generate_prompt_few_shot(comment) for comment in example['comments']]
    example['input_ids'] = tokenizer(prompt, padding="max_length", truncation=True, return_tensors="pt").input_ids
    example['labels'] = tokenizer(example['responses'], padding="max_length", truncation=True, return_tensors="pt").input_ids
    return example

tokenized_datasets = dataset.map(tokenize_function, batched=True)
tokenized_datasets = tokenized_datasets.remove_columns(['comments', 'responses',])

Map:   0%|          | 0/3202 [00:00<?, ? examples/s]


# Saving and Loading
#tokenized_datasets.save_to_disk("data/fine_tunning_data/tokenized_datasets")
tokenized_datasets = datasets.load_from_disk("data/fine_tunning_data/tokenized_datasets")

Saving the dataset (0/1 shards):   0%|          | 0/3202 [00:00<?, ? examples/s]


tokenized_datasets

Dataset({
    features: ['input_ids', 'labels'],
    num_rows: 3202
})


lora_config = LoraConfig(
    r=256, # Rank
    lora_alpha=32,
    target_modules=["q", "v"],
    lora_dropout=0.05,
    bias="none",
    task_type=TaskType.SEQ_2_SEQ_LM # FLAN-T5
)
peft_model = get_peft_model(original_model, lora_config)


def print_number_of_trainable_model_parameters(model):
    trainable_model_params = 0
    all_model_params = 0
    for _, param in model.named_parameters():
        all_model_params += param.numel()
        if param.requires_grad:
            trainable_model_params += param.numel()
    return f"trainable model parameters: {trainable_model_params}\nall model parameters: {all_model_params}\npercentage of trainable model parameters: {100 * trainable_model_params / all_model_params:.2f}%"
print(print_number_of_trainable_model_parameters(peft_model))

trainable model parameters: 28311552
all model parameters: 275889408
percentage of trainable model parameters: 10.26%


output_dir = f'data/models/fine_tunned_flan_t5/comments-response-training-{str(int(time.time()))}'

peft_training_args = TrainingArguments(
    output_dir=output_dir,
    auto_find_batch_size=True,
    learning_rate=1e-3, # Higher learning rate than full fine-tuning.
    num_train_epochs=10,
    logging_steps=1,
    max_steps=10    
)
    
peft_trainer = Trainer(
    model=peft_model,
    args=peft_training_args,
    train_dataset=tokenized_datasets,
)


peft_trainer.train()

TrainOutput(global_step=10, training_loss=37.6625, metrics={'train_runtime': 673.558, 'train_samples_per_second': 0.119, 'train_steps_per_second': 0.015, 'total_flos': 58259511705600.0, 'train_loss': 37.6625, 'epoch': 0.02})


peft_model_path="data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local"

#peft_trainer.model.save_pretrained(peft_model_path)
#tokenizer.save_pretrained(peft_model_path)

('data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local/tokenizer_config.json',
 'data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local/special_tokens_map.json',
 'data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local/spiece.model',
 'data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local/added_tokens.json',
 'data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local/tokenizer.json')


peft_model_base = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base", torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")

peft_model = PeftModel.from_pretrained(peft_model_base, 
                                       'data/models/fine_tunned_flan_t5/peft-comment-response-checkpoint-local/', 
                                       torch_dtype=torch.bfloat16,
                                       is_trainable=False)


print(print_number_of_trainable_model_parameters(peft_model))

trainable model parameters: 0
all model parameters: 261733632
percentage of trainable model parameters: 0.00%


def generate_respond(comment, model, tokenizer):
    prompt = generate_prompt_few_shot(comment)
    input_ids = tokenizer(prompt, return_tensors='pt').input_ids
    output = tokenizer.decode(
        model.generate(
            input_ids = input_ids, 
            generation_config=GenerationConfig(max_new_tokens=500,
            do_sample=True,
            temperature= 0.7),
        )[0], 
        skip_special_tokens=True
    )

    return output

peft_results = {}
for comment, response in tqdm(zip(test_comments, test_responses)): 
    output = generate_respond(comment, peft_model, tokenizer)
    peft_results[comment] = {"human": response, "peft_model": output}

0it [00:00, ?it/s]


pd.set_option('display.max_colwidth', 500)
peft_model_response = pd.DataFrame.from_dict(peft_results).T.reset_index()
peft_model_response = peft_model_response.rename(columns={"index":"comment"})


all_models_response = pd.merge(original_model_reponse, peft_model_response, on=['comment', 'human'])
all_models_response


def evaluate_qa(predictions, references):
    rouge = evaluate.load('rouge')
    original_model_results = rouge.compute(
        predictions=predictions,
        references=references,
        use_aggregator=True,
        use_stemmer=True,
    )
    return original_model_results


peft_model_dict = evaluate_qa(all_models_response['peft_model'], all_models_response['human'])
original_model_dict = evaluate_qa(all_models_response['original_model'], all_models_response['human'])


keys = list(peft_model_dict.keys())
values_peft_model = list(peft_model_dict.values())
values_original_model = list(original_model_dict.values())

fig = go.Figure()
fig.add_trace(go.Bar(x=keys, y=values_peft_model, name='PEFT Model'))
fig.add_trace(go.Bar(x=keys, y=values_original_model, name='Original Model'))

fig.update_layout(title='Comparison of PEFT Model and Original Model by ROUGE metric',
                  xaxis_title='ROUGE Metric',
                  yaxis_title='ROUGE Score',
                  barmode='group')
fig.show()

	tweet_id	author_id	inbound	created_at	text	response_tweet_id	in_response_to_tweet_id
0	1	sprintcare	False	Tue Oct 31 22:10:47 +0000 2017	@115712 I understand. I would like to assist you. We would need to get you into a private secured link to further assist.	2	3.0
1	2	115712	True	Tue Oct 31 22:11:45 +0000 2017	@sprintcare and how do you propose we do that	NaN	1.0
2	3	115712	True	Tue Oct 31 22:08:27 +0000 2017	@sprintcare I have sent several private messages and no one is responding as usual	1	4.0
3	4	sprintcare	False	Tue Oct 31 21:54:49 +0000 2017	@115712 Please send us a Private Message so that we can further assist you. Just click ‘Message’ at the top of your profile.	3	5.0
4	5	115712	True	Tue Oct 31 21:49:35 +0000 2017	@sprintcare I did.	4	6.0

	tweet_id	in_response_to_tweet_id
count	2.811774e+06	2.017439e+06
mean	1.504565e+06	1.463141e+06
std	8.616450e+05	8.665730e+05
min	1.000000e+00	1.000000e+00
25%	7.601652e+05	7.155105e+05
50%	1.507772e+06	1.439805e+06
75%	2.253296e+06	2.220646e+06
max	2.987950e+06	2.987950e+06

	tweet_id	author_id	inbound	created_at	text	response_tweet_id	in_response_to_tweet_id	date
0	1	sprintcare	False	Tue Oct 31 22:10:47 +0000 2017	i understand. i would like to assist you. we would need to get you into a private secured link to further assist.	2	3.0	2017-10-31 22:10:47
1	2	115712	True	Tue Oct 31 22:11:45 +0000 2017	and how do you propose we do that	NaN	1.0	2017-10-31 22:11:45
2	3	115712	True	Tue Oct 31 22:08:27 +0000 2017	i have sent several private messages and no one is responding as usual	1	4.0	2017-10-31 22:08:27
3	4	sprintcare	False	Tue Oct 31 21:54:49 +0000 2017	please send us a private message so that we can further assist you. just click message at the top of your profile.	3	5.0	2017-10-31 21:54:49
4	5	115712	True	Tue Oct 31 21:49:35 +0000 2017	i did.	4	6.0	2017-10-31 21:49:35

	Topic	Count	Name	Representation	Representative_Docs
0	-1	181183	-1_url_please_us_help	[url, please, us, help, thanks]	NaN
1	0	11890	0_dm_us dm_us_send us	[dm, us dm, us, send us, send]	NaN
2	1	8891	1_driver_uber_ride_drivers	[driver, uber, ride, drivers, lyft]	NaN
3	2	8817	2_de_que_en_la	[de, que, en, la, el]	NaN
4	3	6222	3_spotify_music_songs_song	[spotify, music, songs, song, playlist]	NaN
...	...	...	...	...	...
187	186	269	186_iphone_freezing_update_ios update	[iphone, freezing, update, ios update, ios]	NaN
188	187	267	187_dell_laptop_warranty_inspiron	[dell, laptop, warranty, inspiron, laptops]	NaN
189	188	266	188_aadhar_aadhaar_stream yet_check singles	[aadhar, aadhaar, stream yet, check singles, s...	NaN
190	189	266	189_return_replacement_item_options url	[return, replacement, item, options url, options]	NaN
191	190	262	190_today_pm_tomorrow_8pm	[today, pm, tomorrow, 8pm, day]	NaN

	comment	human	original_model
0	order says it was delivered last night at 20.45 however at this time i was on a call with amazon customer service. still no delivery	i'm sorry you haven't received your package yet. when you spoke with us, what options did we provide? ay	I have sent you the order number and your order number, but I wasn't able to find it. I have tried searching and contacting amazon customer service, but the package has not been delivered to my address.
1	my parcel hasn't arrived and the tracking message is poor 'probably arrived as we expected to be there by now'?? vague?	were there any emails sent to you regarding this order? if yes, did it advise of any delays? ma	What would you like to know about the problem with your order?
2	still waiting for my copy of the new book despite pre ordering. amazon need to get their shit together	hi nick, were you provided with a delivery date? tp	I'm sorry to hear that. I'm concerned about the products you're requesting. You can expect to receive your order in a few days.
3	- delivery notices showing what was delivered on my kids kindles is a terrible idea. unfortunately, the team in india cannot help me turn off delivery notifications...on my 4th person and probably further away from resolution	oh my! do you have the amazon app on the device? if so, have you tried turning those notifcations off? let us know, we want to help! mt	I know you're not making good use of that service. How do you feel about the inconvenience?
4	dear . sick of ordering items to find, after paying, they are coming from china and take weeks!!	so sorry about this. we do aim to deliver by the delivery date given at the time the order was placed. km	I understand, but what I do want to do is to help you resolve your issue.
5	can you explain why my delivery was thrown over my back gate open!?there was no note left either to say where it wasdelivered.	i'm so sorry it was delivered like this! was any portion of your order damaged or missing? jr	Thank you so much for the response. I hope you're all okay.
6	please can you look into this order: 206-9303243-6219526 i paid for next day delivery and still not received!! i would like 12	we do not have access to account information on this platform, claire. what date were you given for the delivery of this order? is this item fulfilled by amazon or a seller?sm	I'm sorry to hear that.
7	tracking id q54023807103 if it was out for delivery yesterday why do i have to wait until tuesday?	hi, sorry to hear that, what was the estimated delivery date stated on the order confirmation email? jj	Your order was shipped yesterday, did you receive the package?
8	experience on-time correct order missing item delivered to door said he couldn't come in bc of other deliveries pleasant courier bonus	sorry to hear about your experience, please send us a note here: the url and we'll look into this further.	We were able to correct the issue in the delivery times.
9	you missed delivering a package to my work address. i dont know how but can you hold my package at the facility so i can pick it up tonight?	please dm us details of your concern or compliment include your tracking and phone number. don't forget to provide your shipping address. lg the url	I can put in the information on your account.
10	hey my package is literally right next door. less than 5 miles away. why would it take two days to deliver that??? the url	our team would like to research more, please dm the tracking number, address, and telephone number. tv the url	That is a problem. What is the best way to address this issue?
11	so after a 3rd terrible experience with deliveries i will be taking my custom elsewhere from now on poorservice disappointed	we'd love to help out in any way we can! without sharing accountpersonal details, can you please tell us what happened? wj	I have tried this store twice now, both times I was not satisfied.
12	pathetic service by , order should have delivered by 28 oct but no body including dnt know whr my order is. superannoyed loss paying extra money to stay at delivery address. order no: 204-4348609-9182765	i'm sorry for the frustrating experience! did our customer service set any expectations for the parceldelivery? mj	Sorry to hear that. I can help you on your request.
13	this is the 2nd time my prime membership let me down. placed order on 09112017 and still not delivered! amazonprime the url	oh no! i'm sorry that your packages have been delayed. product availability, severe weather, and carrier capacity can all affect your delivery date. please reach out to us here for further assistance: the url sp	What's up with this?
14	my package has been in china since the 29th and its suppose to be here in the usa by the 3rd? whats going on???	please dm us details of your concern or compliment include your tracking and phone number. we're here to help. lg the url	I will try to pick up your package from china by the 3rd.
15	package said it will be delivered by end of day it's already 930pm pacific time still no package what's going on?	i understand how upsetting this must be. we are working to process and deliver packages as best we can. i do apologize for any inconvenience this delay has caused. ea the url	Wait for your package to arrive and you'll be able to get it.
16	has anyone noticed 'guaranteed delivery' dates have been slipping by a lot lately? ominous holiday troubles ahead?	i'm sorry to hear this! have you reported these late orders to our customer support team? if so, what information was provided? ez	Oh no, not a lot! I've asked for a new item and it says 'guaranteed delivery'. Could you please tell me what are the reasons?
17	dear , you should highly reconsider sending my prime orders through . nothing is ever delivered in two days... sincerely, where the fuck is my package	thanks for reaching out to us. what was the delivery date we gave you for this order?sm	That's okay, thank you for choosing Amazon.
18	i've been waiting in all day for a delivery, i've just checked on it and it says an attempt was made..uhh no there wasn't	oh no! let's try reaching out to the courier to get some additional information: the url fd	Thank you. I wish I could help you.
19	hi there... it's embarrassing that i filed a return 17th due to defective product.. however i am still waiting...	we're sorry for the delay, yogesh. was a pick up scheduled for your product? if yes, when was it due? hk	You're welcome. Have a nice day!
20	amazon emailed me that my laptop charger delivery date has been delayed. i ordered it sept 26th with two day shipping.	i'm sorry for the delay! which carrier is assigned to your order? does the tracking on their website give any clarity? mv	Thank you. I hope you are fine.
21	why pay for prime and not get your package in 2 days?? come on..	two-day shipping refers to transit time, in business days, once shipped. have we missed your confirmed delivery date? am	Sorry for the inconvenience.
22	hi there, can someone else collect my dpd parcel in your winterstoke road store if they take my id and reference number?	hi meg, that shouldn't be a problem, but to double check, i'd recommend giving the store a call directly on 0117 966 3064. danny	Thank you for your help.
23	how do i get a refund on shipping? ordered overnight shipping and it took an extra few days! thanks for your help!	we're here to help, sorry for the wait! have we missed our expected delivery date provided here: the url ? please, let us know! je	Yes, I am trying to get refunds on your order. Can you email me your refund and receipt?
24	had e-mail from amazonshipping attempted to deliver and failed. sitting in my office next to the front door! no delivery attempt!	i'm sorry to hear about the problem with this delivery! for further assistance, please use this: the url th	Thanks!

Enhancing Customer Service Support with an Intelligent AI Assistant¶

Data Selection¶

Data Charactristics¶

Bussiness Value¶

Exploratiory Data Analysis¶

1. Data Distribution Amongs Company's Names¶

2. Data Distribution W.r.t Date¶

Data Filtering¶

Text Data Cleaning¶

Retriving Conversations¶

Topic Modeling¶

BertTopic¶

Filtering Conversations by Topics¶

Building an AI assistant using Large Language Models (LLMs).¶

Prepare the data in the form of comment and response¶

Load the pre-trained model¶

Conduct an In-Context Learning¶

Fine Tunning¶

Build and formatting the the dataset to feed the model¶

Paramater Efficient Fine Tunning¶

Qualitative Evaluation¶

Quantitive Evaluation¶

Disscusion¶

	tweet_id	author_id	inbound	created_at	text	response_tweet_id	in_response_to_tweet_id	date
6	8	115712	True	Tue Oct 31 21:45:10 +0000 2017	is the worst customer service	9,6,10	NaN	2017-10-31 21:45:10
12	18	115713	True	Tue Oct 31 19:56:01 +0000 2017	yall lie about your great connection. 5 bars l...	17	NaN	2017-10-31 19:56:01
14	20	115715	True	Tue Oct 31 22:03:34 +0000 2017	whenever i contact customer support, they tell...	19	NaN	2017-10-31 22:03:34
23	29	115716	True	Tue Oct 31 22:01:35 +0000 2017	actually that's a broken link you sent me and ...	28	NaN	2017-10-31 22:01:35
25	31	115717	True	Tue Oct 31 22:06:54 +0000 2017	yo , your customer service reps are super nice...	30	NaN	2017-10-31 22:06:54

Step	Training Loss
1	47.500000
2	46.500000
3	43.750000
4	39.250000
5	36.750000
6	34.750000
7	33.500000
8	32.250000
9	31.500000
10	30.875000